Coverage for /var/srv/projects/api.amasfac.comuna18.com/tmp/venv/lib/python3.9/site-packages/phonenumbers/unicode_util.py: 90%
297 statements
« prev ^ index » next coverage.py v6.4.4, created at 2023-07-17 14:22 -0600
1"""Unicode utility functions
3>>> from .import unicode_util
4>>> from .util import u
5>>> u1 = '1' # DIGIT ONE
6>>> u2 = u('a') # LATIN SMALL LETTER A
7>>> u3 = u('\uFF12') # FULLWIDTH DIGIT TWO
8>>> u4 = u('\u0100') # LATIN CAPITAL LETTER A WITH MACRON
9>>> unicode_util.Category.get(u1) == u('Nd')
10True
11>>> unicode_util.Category.get(u2) == u('Ll')
12True
13>>> unicode_util.Category.get(u3) == u('Nd')
14True
15>>> unicode_util.Category.get(u4) == u('Lu')
16True
17>>> unicode_util.Category.get(u2) == unicode_util.Category.LOWERCASE_LETTER
18True
19>>> try:
20... beyond_bmp = u('\U00010100') # AEGEAN WORD SEPARATOR LINE
21... except Exception:
22... beyond_bmp = u('')
23>>> if len(beyond_bmp) == 1: # We have a UCS4 build of Python
24... cat_po = unicode_util.Category.get(beyond_bmp)
25... else: # UCS2 build of Python; no non-BMP chars available
26... cat_po = unicode_util.Category.OTHER_PUNCTUATION
27>>> cat_po == u('Po')
28True
29>>> unicode_util.is_letter(u1)
30False
31>>> unicode_util.is_letter(u2)
32True
33>>> unicode_util.is_letter(u3)
34False
35>>> unicode_util.is_letter(u4)
36True
37>>> b1 = unicode_util.Block.get(u1)
38>>> str(b1)
39'Block[0000, 007f]'
40>>> b1 == unicode_util.Block.BASIC_LATIN
41True
42>>> b1 == [0x0000, 0x0075]
43False
44>>> b2 = unicode_util.Block.get(u2)
45>>> b2 == unicode_util.Block.BASIC_LATIN
46True
47>>> b3 = unicode_util.Block.get(u3)
48>>> b3 != unicode_util.Block.BASIC_LATIN
49True
50>>> b3 == unicode_util.Block.HALFWIDTH_AND_FULLWIDTH_FORMS
51True
52>>> b4 = unicode_util.Block.get(u4)
53>>> b4 == unicode_util.Block.LATIN_EXTENDED_A
54True
55>>> unicode_util.Block.get(u('\u0860')) == unicode_util.Block.UNKNOWN
56True
57>>> try:
58... unknown_block = u('\U00013430')
59... except Exception:
60... unknown_block = u('')
61>>> if len(unknown_block) == 1: # We have a UCS4 build of Python
62... unicode_util.Block.get(u('\U00013430')) == unicode_util.Block.UNKNOWN
63... else: # UCS2 build of Python; no unknown characters available
64... True
65True
66>>> unicode_util.digit(u1)
671
68>>> unicode_util.digit(u2, -1)
69-1
70>>> unicode_util.digit(u3, -1)
712
72>>> str(hash(b3)) # doctest: +ELLIPSIS
73'...'
74"""
75import bisect
76import unicodedata
78from .util import UnicodeMixin, unicod, u
81class Category(object):
82 """General category of a Unicode character.
84 See http://www.unicode.org/reports/tr18/#Categories"""
85 LETTER = u("L")
86 UPPERCASE_LETTER = u("Lu")
87 LOWERCASE_LETTER = u("Ll")
88 TITLECASE_LETTER = u("Lt")
89 MODIFIER_LETTER = u("Lm")
90 OTHER_LETTER = u("Lo")
91 MARK = u("M")
92 NON_SPACING_MARK = u("Mn")
93 SPACING_COMBINING_MARK = u("Mc")
94 ENCLOSING_MARK = u("Me")
95 NUMBER = u("N")
96 DECIMAL_DIGIT_NUMBER = u("Nd")
97 LETTER_NUMBER = u("Nl")
98 OTHER_NUMBER = u("No")
99 SYMBOL = u("S")
100 MATH_SYMBOL = u("Sm")
101 CURRENCY_SYMBOL = u("Sc")
102 MODIFIER_SYMBOL = u("Sk")
103 OTHER_SYMBOL = u("So")
104 PUNCTUATION = u("P")
105 CONNECTOR_PUNCTUATION = u("Pc")
106 DASH_PUNCTUATION = u("Pd")
107 OPEN_PUNCTUATION = u("Ps")
108 CLOSE_PUNCTUATION = u("Pe")
109 INITIAL_PUNCTUATION = u("Pi")
110 FINAL_PUNCTUATION = u("Pf")
111 OTHER_PUNCTUATION = u("Po")
112 SEPARATOR = u("Z")
113 SPACE_SEPARATOR = u("Zs")
114 LINE_SEPARATOR = u("Zl")
115 PARAGRAPH_SEPARATOR = u("Zp")
116 OTHER = u("C")
117 CONTROL = u("Cc")
118 FORMAT = u("Cf")
119 SURROGATE = u("Cs")
120 PRIVATE_USE = u("Co")
121 NOT_ASSIGNED = u("Cn")
123 @classmethod
124 def get(cls, uni_char):
125 """Return the general category code (as Unicode string) for the given Unicode character"""
126 uni_char = unicod(uni_char) # Force to Unicode
127 return unicod(unicodedata.category(uni_char))
130def is_letter(uni_char):
131 """Determine whether the given Unicode character is a Unicode letter"""
132 category = Category.get(uni_char)
133 return (category == Category.UPPERCASE_LETTER or
134 category == Category.LOWERCASE_LETTER or
135 category == Category.TITLECASE_LETTER or
136 category == Category.MODIFIER_LETTER or
137 category == Category.OTHER_LETTER)
140class _BlockRange(UnicodeMixin):
141 """Describe the range of characters encompassed by a Unicode block"""
142 def __init__(self, start, end, regdict=None):
143 self.start = start
144 self.end = end
145 if regdict is not None:
146 regdict[start] = self
148 def __eq__(self, other):
149 if not isinstance(other, _BlockRange):
150 return NotImplemented
151 return (self.start == other.start and self.end == other.end)
153 def __ne__(self, other):
154 return not self == other
156 def __hash__(self):
157 return hash((self.start, self.end))
159 def __unicode__(self):
160 return unicod("Block[%04x, %04x]") % (self.start, self.end)
163class Block(object):
164 """Description of the possible Unicode blocks"""
166 _RANGES = {} # lower end of range => _BlockRange object
167 _RANGE_KEYS = None # sorted list of _RANGES.keys()
169 # Taken from http://www.unicode.org/Public/UNIDATA/Blocks.txt
170 BASIC_LATIN = _BlockRange(0x0000, 0x007F, _RANGES)
171 LATIN_1_SUPPLEMENT = _BlockRange(0x0080, 0x00FF, _RANGES)
172 LATIN_EXTENDED_A = _BlockRange(0x0100, 0x017F, _RANGES)
173 LATIN_EXTENDED_B = _BlockRange(0x0180, 0x024F, _RANGES)
174 IPA_EXTENSIONS = _BlockRange(0x0250, 0x02AF, _RANGES)
175 SPACING_MODIFIER_LETTERS = _BlockRange(0x02B0, 0x02FF, _RANGES)
176 COMBINING_DIACRITICAL_MARKS = _BlockRange(0x0300, 0x036F, _RANGES)
177 GREEK_AND_COPTIC = _BlockRange(0x0370, 0x03FF, _RANGES)
178 CYRILLIC = _BlockRange(0x0400, 0x04FF, _RANGES)
179 CYRILLIC_SUPPLEMENT = _BlockRange(0x0500, 0x052F, _RANGES)
180 ARMENIAN = _BlockRange(0x0530, 0x058F, _RANGES)
181 HEBREW = _BlockRange(0x0590, 0x05FF, _RANGES)
182 ARABIC = _BlockRange(0x0600, 0x06FF, _RANGES)
183 SYRIAC = _BlockRange(0x0700, 0x074F, _RANGES)
184 ARABIC_SUPPLEMENT = _BlockRange(0x0750, 0x077F, _RANGES)
185 THAANA = _BlockRange(0x0780, 0x07BF, _RANGES)
186 NKO = _BlockRange(0x07C0, 0x07FF, _RANGES)
187 SAMARITAN = _BlockRange(0x0800, 0x083F, _RANGES)
188 MANDAIC = _BlockRange(0x0840, 0x085F, _RANGES)
189 DEVANAGARI = _BlockRange(0x0900, 0x097F, _RANGES)
190 BENGALI = _BlockRange(0x0980, 0x09FF, _RANGES)
191 GURMUKHI = _BlockRange(0x0A00, 0x0A7F, _RANGES)
192 GUJARATI = _BlockRange(0x0A80, 0x0AFF, _RANGES)
193 ORIYA = _BlockRange(0x0B00, 0x0B7F, _RANGES)
194 TAMIL = _BlockRange(0x0B80, 0x0BFF, _RANGES)
195 TELUGU = _BlockRange(0x0C00, 0x0C7F, _RANGES)
196 KANNADA = _BlockRange(0x0C80, 0x0CFF, _RANGES)
197 MALAYALAM = _BlockRange(0x0D00, 0x0D7F, _RANGES)
198 SINHALA = _BlockRange(0x0D80, 0x0DFF, _RANGES)
199 THAI = _BlockRange(0x0E00, 0x0E7F, _RANGES)
200 LAO = _BlockRange(0x0E80, 0x0EFF, _RANGES)
201 TIBETAN = _BlockRange(0x0F00, 0x0FFF, _RANGES)
202 MYANMAR = _BlockRange(0x1000, 0x109F, _RANGES)
203 GEORGIAN = _BlockRange(0x10A0, 0x10FF, _RANGES)
204 HANGUL_JAMO = _BlockRange(0x1100, 0x11FF, _RANGES)
205 ETHIOPIC = _BlockRange(0x1200, 0x137F, _RANGES)
206 ETHIOPIC_SUPPLEMENT = _BlockRange(0x1380, 0x139F, _RANGES)
207 CHEROKEE = _BlockRange(0x13A0, 0x13FF, _RANGES)
208 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = _BlockRange(0x1400, 0x167F, _RANGES)
209 OGHAM = _BlockRange(0x1680, 0x169F, _RANGES)
210 RUNIC = _BlockRange(0x16A0, 0x16FF, _RANGES)
211 TAGALOG = _BlockRange(0x1700, 0x171F, _RANGES)
212 HANUNOO = _BlockRange(0x1720, 0x173F, _RANGES)
213 BUHID = _BlockRange(0x1740, 0x175F, _RANGES)
214 TAGBANWA = _BlockRange(0x1760, 0x177F, _RANGES)
215 KHMER = _BlockRange(0x1780, 0x17FF, _RANGES)
216 MONGOLIAN = _BlockRange(0x1800, 0x18AF, _RANGES)
217 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = _BlockRange(0x18B0, 0x18FF, _RANGES)
218 LIMBU = _BlockRange(0x1900, 0x194F, _RANGES)
219 TAI_LE = _BlockRange(0x1950, 0x197F, _RANGES)
220 NEW_TAI_LUE = _BlockRange(0x1980, 0x19DF, _RANGES)
221 KHMER_SYMBOLS = _BlockRange(0x19E0, 0x19FF, _RANGES)
222 BUGINESE = _BlockRange(0x1A00, 0x1A1F, _RANGES)
223 TAI_THAM = _BlockRange(0x1A20, 0x1AAF, _RANGES)
224 BALINESE = _BlockRange(0x1B00, 0x1B7F, _RANGES)
225 SUNDANESE = _BlockRange(0x1B80, 0x1BBF, _RANGES)
226 BATAK = _BlockRange(0x1BC0, 0x1BFF, _RANGES)
227 LEPCHA = _BlockRange(0x1C00, 0x1C4F, _RANGES)
228 OL_CHIKI = _BlockRange(0x1C50, 0x1C7F, _RANGES)
229 VEDIC_EXTENSIONS = _BlockRange(0x1CD0, 0x1CFF, _RANGES)
230 PHONETIC_EXTENSIONS = _BlockRange(0x1D00, 0x1D7F, _RANGES)
231 PHONETIC_EXTENSIONS_SUPPLEMENT = _BlockRange(0x1D80, 0x1DBF, _RANGES)
232 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = _BlockRange(0x1DC0, 0x1DFF, _RANGES)
233 LATIN_EXTENDED_ADDITIONAL = _BlockRange(0x1E00, 0x1EFF, _RANGES)
234 GREEK_EXTENDED = _BlockRange(0x1F00, 0x1FFF, _RANGES)
235 GENERAL_PUNCTUATION = _BlockRange(0x2000, 0x206F, _RANGES)
236 SUPERSCRIPTS_AND_SUBSCRIPTS = _BlockRange(0x2070, 0x209F, _RANGES)
237 CURRENCY_SYMBOLS = _BlockRange(0x20A0, 0x20CF, _RANGES)
238 COMBINING_DIACRITICAL_MARKS_FOR_SYMBOLS = _BlockRange(0x20D0, 0x20FF, _RANGES)
239 LETTERLIKE_SYMBOLS = _BlockRange(0x2100, 0x214F, _RANGES)
240 NUMBER_FORMS = _BlockRange(0x2150, 0x218F, _RANGES)
241 ARROWS = _BlockRange(0x2190, 0x21FF, _RANGES)
242 MATHEMATICAL_OPERATORS = _BlockRange(0x2200, 0x22FF, _RANGES)
243 MISCELLANEOUS_TECHNICAL = _BlockRange(0x2300, 0x23FF, _RANGES)
244 CONTROL_PICTURES = _BlockRange(0x2400, 0x243F, _RANGES)
245 OPTICAL_CHARACTER_RECOGNITION = _BlockRange(0x2440, 0x245F, _RANGES)
246 ENCLOSED_ALPHANUMERICS = _BlockRange(0x2460, 0x24FF, _RANGES)
247 BOX_DRAWING = _BlockRange(0x2500, 0x257F, _RANGES)
248 BLOCK_ELEMENTS = _BlockRange(0x2580, 0x259F, _RANGES)
249 GEOMETRIC_SHAPES = _BlockRange(0x25A0, 0x25FF, _RANGES)
250 MISCELLANEOUS_SYMBOLS = _BlockRange(0x2600, 0x26FF, _RANGES)
251 DINGBATS = _BlockRange(0x2700, 0x27BF, _RANGES)
252 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = _BlockRange(0x27C0, 0x27EF, _RANGES)
253 SUPPLEMENTAL_ARROWS_A = _BlockRange(0x27F0, 0x27FF, _RANGES)
254 BRAILLE_PATTERNS = _BlockRange(0x2800, 0x28FF, _RANGES)
255 SUPPLEMENTAL_ARROWS_B = _BlockRange(0x2900, 0x297F, _RANGES)
256 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = _BlockRange(0x2980, 0x29FF, _RANGES)
257 SUPPLEMENTAL_MATHEMATICAL_OPERATORS = _BlockRange(0x2A00, 0x2AFF, _RANGES)
258 MISCELLANEOUS_SYMBOLS_AND_ARROWS = _BlockRange(0x2B00, 0x2BFF, _RANGES)
259 GLAGOLITIC = _BlockRange(0x2C00, 0x2C5F, _RANGES)
260 LATIN_EXTENDED_C = _BlockRange(0x2C60, 0x2C7F, _RANGES)
261 COPTIC = _BlockRange(0x2C80, 0x2CFF, _RANGES)
262 GEORGIAN_SUPPLEMENT = _BlockRange(0x2D00, 0x2D2F, _RANGES)
263 TIFINAGH = _BlockRange(0x2D30, 0x2D7F, _RANGES)
264 ETHIOPIC_EXTENDED = _BlockRange(0x2D80, 0x2DDF, _RANGES)
265 CYRILLIC_EXTENDED_A = _BlockRange(0x2DE0, 0x2DFF, _RANGES)
266 SUPPLEMENTAL_PUNCTUATION = _BlockRange(0x2E00, 0x2E7F, _RANGES)
267 CJK_RADICALS_SUPPLEMENT = _BlockRange(0x2E80, 0x2EFF, _RANGES)
268 KANGXI_RADICALS = _BlockRange(0x2F00, 0x2FDF, _RANGES)
269 IDEOGRAPHIC_DESCRIPTION_CHARACTERS = _BlockRange(0x2FF0, 0x2FFF, _RANGES)
270 CJK_SYMBOLS_AND_PUNCTUATION = _BlockRange(0x3000, 0x303F, _RANGES)
271 HIRAGANA = _BlockRange(0x3040, 0x309F, _RANGES)
272 KATAKANA = _BlockRange(0x30A0, 0x30FF, _RANGES)
273 BOPOMOFO = _BlockRange(0x3100, 0x312F, _RANGES)
274 HANGUL_COMPATIBILITY_JAMO = _BlockRange(0x3130, 0x318F, _RANGES)
275 KANBUN = _BlockRange(0x3190, 0x319F, _RANGES)
276 BOPOMOFO_EXTENDED = _BlockRange(0x31A0, 0x31BF, _RANGES)
277 CJK_STROKES = _BlockRange(0x31C0, 0x31EF, _RANGES)
278 KATAKANA_PHONETIC_EXTENSIONS = _BlockRange(0x31F0, 0x31FF, _RANGES)
279 ENCLOSED_CJK_LETTERS_AND_MONTHS = _BlockRange(0x3200, 0x32FF, _RANGES)
280 CJK_COMPATIBILITY = _BlockRange(0x3300, 0x33FF, _RANGES)
281 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = _BlockRange(0x3400, 0x4DBF, _RANGES)
282 YIJING_HEXAGRAM_SYMBOLS = _BlockRange(0x4DC0, 0x4DFF, _RANGES)
283 CJK_UNIFIED_IDEOGRAPHS = _BlockRange(0x4E00, 0x9FFF, _RANGES)
284 YI_SYLLABLES = _BlockRange(0xA000, 0xA48F, _RANGES)
285 YI_RADICALS = _BlockRange(0xA490, 0xA4CF, _RANGES)
286 LISU = _BlockRange(0xA4D0, 0xA4FF, _RANGES)
287 VAI = _BlockRange(0xA500, 0xA63F, _RANGES)
288 CYRILLIC_EXTENDED_B = _BlockRange(0xA640, 0xA69F, _RANGES)
289 BAMUM = _BlockRange(0xA6A0, 0xA6FF, _RANGES)
290 MODIFIER_TONE_LETTERS = _BlockRange(0xA700, 0xA71F, _RANGES)
291 LATIN_EXTENDED_D = _BlockRange(0xA720, 0xA7FF, _RANGES)
292 SYLOTI_NAGRI = _BlockRange(0xA800, 0xA82F, _RANGES)
293 COMMON_INDIC_NUMBER_FORMS = _BlockRange(0xA830, 0xA83F, _RANGES)
294 PHAGS_PA = _BlockRange(0xA840, 0xA87F, _RANGES)
295 SAURASHTRA = _BlockRange(0xA880, 0xA8DF, _RANGES)
296 DEVANAGARI_EXTENDED = _BlockRange(0xA8E0, 0xA8FF, _RANGES)
297 KAYAH_LI = _BlockRange(0xA900, 0xA92F, _RANGES)
298 REJANG = _BlockRange(0xA930, 0xA95F, _RANGES)
299 HANGUL_JAMO_EXTENDED_A = _BlockRange(0xA960, 0xA97F, _RANGES)
300 JAVANESE = _BlockRange(0xA980, 0xA9DF, _RANGES)
301 CHAM = _BlockRange(0xAA00, 0xAA5F, _RANGES)
302 MYANMAR_EXTENDED_A = _BlockRange(0xAA60, 0xAA7F, _RANGES)
303 TAI_VIET = _BlockRange(0xAA80, 0xAADF, _RANGES)
304 ETHIOPIC_EXTENDED_A = _BlockRange(0xAB00, 0xAB2F, _RANGES)
305 MEETEI_MAYEK = _BlockRange(0xABC0, 0xABFF, _RANGES)
306 HANGUL_SYLLABLES = _BlockRange(0xAC00, 0xD7AF, _RANGES)
307 HANGUL_JAMO_EXTENDED_B = _BlockRange(0xD7B0, 0xD7FF, _RANGES)
308 HIGH_SURROGATES = _BlockRange(0xD800, 0xDB7F, _RANGES)
309 HIGH_PRIVATE_USE_SURROGATES = _BlockRange(0xDB80, 0xDBFF, _RANGES)
310 LOW_SURROGATES = _BlockRange(0xDC00, 0xDFFF, _RANGES)
311 PRIVATE_USE_AREA = _BlockRange(0xE000, 0xF8FF, _RANGES)
312 CJK_COMPATIBILITY_IDEOGRAPHS = _BlockRange(0xF900, 0xFAFF, _RANGES)
313 ALPHABETIC_PRESENTATION_FORMS = _BlockRange(0xFB00, 0xFB4F, _RANGES)
314 ARABIC_PRESENTATION_FORMS_A = _BlockRange(0xFB50, 0xFDFF, _RANGES)
315 VARIATION_SELECTORS = _BlockRange(0xFE00, 0xFE0F, _RANGES)
316 VERTICAL_FORMS = _BlockRange(0xFE10, 0xFE1F, _RANGES)
317 COMBINING_HALF_MARKS = _BlockRange(0xFE20, 0xFE2F, _RANGES)
318 CJK_COMPATIBILITY_FORMS = _BlockRange(0xFE30, 0xFE4F, _RANGES)
319 SMALL_FORM_VARIANTS = _BlockRange(0xFE50, 0xFE6F, _RANGES)
320 ARABIC_PRESENTATION_FORMS_B = _BlockRange(0xFE70, 0xFEFF, _RANGES)
321 HALFWIDTH_AND_FULLWIDTH_FORMS = _BlockRange(0xFF00, 0xFFEF, _RANGES)
322 SPECIALS = _BlockRange(0xFFF0, 0xFFFF, _RANGES)
323 LINEAR_B_SYLLABARY = _BlockRange(0x10000, 0x1007F, _RANGES)
324 LINEAR_B_IDEOGRAMS = _BlockRange(0x10080, 0x100FF, _RANGES)
325 AEGEAN_NUMBERS = _BlockRange(0x10100, 0x1013F, _RANGES)
326 ANCIENT_GREEK_NUMBERS = _BlockRange(0x10140, 0x1018F, _RANGES)
327 ANCIENT_SYMBOLS = _BlockRange(0x10190, 0x101CF, _RANGES)
328 PHAISTOS_DISC = _BlockRange(0x101D0, 0x101FF, _RANGES)
329 LYCIAN = _BlockRange(0x10280, 0x1029F, _RANGES)
330 CARIAN = _BlockRange(0x102A0, 0x102DF, _RANGES)
331 OLD_ITALIC = _BlockRange(0x10300, 0x1032F, _RANGES)
332 GOTHIC = _BlockRange(0x10330, 0x1034F, _RANGES)
333 UGARITIC = _BlockRange(0x10380, 0x1039F, _RANGES)
334 OLD_PERSIAN = _BlockRange(0x103A0, 0x103DF, _RANGES)
335 DESERET = _BlockRange(0x10400, 0x1044F, _RANGES)
336 SHAVIAN = _BlockRange(0x10450, 0x1047F, _RANGES)
337 OSMANYA = _BlockRange(0x10480, 0x104AF, _RANGES)
338 CYPRIOT_SYLLABARY = _BlockRange(0x10800, 0x1083F, _RANGES)
339 IMPERIAL_ARAMAIC = _BlockRange(0x10840, 0x1085F, _RANGES)
340 PHOENICIAN = _BlockRange(0x10900, 0x1091F, _RANGES)
341 LYDIAN = _BlockRange(0x10920, 0x1093F, _RANGES)
342 KHAROSHTHI = _BlockRange(0x10A00, 0x10A5F, _RANGES)
343 OLD_SOUTH_ARABIAN = _BlockRange(0x10A60, 0x10A7F, _RANGES)
344 AVESTAN = _BlockRange(0x10B00, 0x10B3F, _RANGES)
345 INSCRIPTIONAL_PARTHIAN = _BlockRange(0x10B40, 0x10B5F, _RANGES)
346 INSCRIPTIONAL_PAHLAVI = _BlockRange(0x10B60, 0x10B7F, _RANGES)
347 OLD_TURKIC = _BlockRange(0x10C00, 0x10C4F, _RANGES)
348 RUMI_NUMERAL_SYMBOLS = _BlockRange(0x10E60, 0x10E7F, _RANGES)
349 BRAHMI = _BlockRange(0x11000, 0x1107F, _RANGES)
350 KAITHI = _BlockRange(0x11080, 0x110CF, _RANGES)
351 CUNEIFORM = _BlockRange(0x12000, 0x123FF, _RANGES)
352 CUNEIFORM_NUMBERS_AND_PUNCTUATION = _BlockRange(0x12400, 0x1247F, _RANGES)
353 EGYPTIAN_HIEROGLYPHS = _BlockRange(0x13000, 0x1342F, _RANGES)
354 BAMUM_SUPPLEMENT = _BlockRange(0x16800, 0x16A3F, _RANGES)
355 KANA_SUPPLEMENT = _BlockRange(0x1B000, 0x1B0FF, _RANGES)
356 BYZANTINE_MUSICAL_SYMBOLS = _BlockRange(0x1D000, 0x1D0FF, _RANGES)
357 MUSICAL_SYMBOLS = _BlockRange(0x1D100, 0x1D1FF, _RANGES)
358 ANCIENT_GREEK_MUSICAL_NOTATION = _BlockRange(0x1D200, 0x1D24F, _RANGES)
359 TAI_XUAN_JING_SYMBOLS = _BlockRange(0x1D300, 0x1D35F, _RANGES)
360 COUNTING_ROD_NUMERALS = _BlockRange(0x1D360, 0x1D37F, _RANGES)
361 MATHEMATICAL_ALPHANUMERIC_SYMBOLS = _BlockRange(0x1D400, 0x1D7FF, _RANGES)
362 MAHJONG_TILES = _BlockRange(0x1F000, 0x1F02F, _RANGES)
363 DOMINO_TILES = _BlockRange(0x1F030, 0x1F09F, _RANGES)
364 PLAYING_CARDS = _BlockRange(0x1F0A0, 0x1F0FF, _RANGES)
365 ENCLOSED_ALPHANUMERIC_SUPPLEMENT = _BlockRange(0x1F100, 0x1F1FF, _RANGES)
366 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = _BlockRange(0x1F200, 0x1F2FF, _RANGES)
367 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = _BlockRange(0x1F300, 0x1F5FF, _RANGES)
368 EMOTICONS = _BlockRange(0x1F600, 0x1F64F, _RANGES)
369 TRANSPORT_AND_MAP_SYMBOLS = _BlockRange(0x1F680, 0x1F6FF, _RANGES)
370 ALCHEMICAL_SYMBOLS = _BlockRange(0x1F700, 0x1F77F, _RANGES)
371 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = _BlockRange(0x20000, 0x2A6DF, _RANGES)
372 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = _BlockRange(0x2A700, 0x2B73F, _RANGES)
373 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = _BlockRange(0x2B740, 0x2B81F, _RANGES)
374 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = _BlockRange(0x2F800, 0x2FA1F, _RANGES)
375 TAGS = _BlockRange(0xE0000, 0xE007F, _RANGES)
376 VARIATION_SELECTORS_SUPPLEMENT = _BlockRange(0xE0100, 0xE01EF, _RANGES)
377 SUPPLEMENTARY_PRIVATE_USE_AREA_A = _BlockRange(0xF0000, 0xFFFFF, _RANGES)
378 SUPPLEMENTARY_PRIVATE_USE_AREA_B = _BlockRange(0x100000, 0x10FFFF, _RANGES)
379 UNKNOWN = _BlockRange(-1, -1)
381 @classmethod
382 def get(cls, uni_char):
383 """Return the Unicode block of the given Unicode character"""
384 uni_char = unicod(uni_char) # Force to Unicode
385 code_point = ord(uni_char)
386 if Block._RANGE_KEYS is None:
387 Block._RANGE_KEYS = sorted(Block._RANGES.keys())
388 idx = bisect.bisect_left(Block._RANGE_KEYS, code_point)
389 if (idx > 0 and
390 code_point >= Block._RANGES[Block._RANGE_KEYS[idx - 1]].start and
391 code_point <= Block._RANGES[Block._RANGE_KEYS[idx - 1]].end):
392 return Block._RANGES[Block._RANGE_KEYS[idx - 1]]
393 elif (idx < len(Block._RANGES) and
394 code_point >= Block._RANGES[Block._RANGE_KEYS[idx]].start and
395 code_point <= Block._RANGES[Block._RANGE_KEYS[idx]].end):
396 return Block._RANGES[Block._RANGE_KEYS[idx]]
397 else:
398 return Block.UNKNOWN
401def digit(uni_char, default_value=None):
402 """Returns the digit value assigned to the Unicode character uni_char as
403 integer. If no such value is defined, default is returned, or, if not
404 given, ValueError is raised."""
405 uni_char = unicod(uni_char) # Force to Unicode.
406 if default_value is not None: 406 ↛ 409line 406 didn't jump to line 409, because the condition on line 406 was never false
407 return unicodedata.digit(uni_char, default_value)
408 else:
409 return unicodedata.digit(uni_char)
412if __name__ == '__main__': # pragma no cover 412 ↛ 413line 412 didn't jump to line 413, because the condition on line 412 was never true
413 import doctest
414 doctest.testmod()